wechat-publisher
一键发布 Markdown 到微信公众号草稿箱。基于 wenyan-cli，支持多主题、代码高亮、图片自动上传。
Install with Tessl CLI
npx tessl i github:NeverSight/skills_feed --skill wechat-publisher71
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description excels at specificity and distinctiveness, clearly identifying a niche use case (WeChat Official Account publishing) with concrete features. The main weakness is the lack of explicit 'Use when...' guidance, which would help Claude know exactly when to select this skill over others.
Suggestions
Add a 'Use when...' clause with trigger terms like '发布到微信', '公众号文章', 'WeChat publishing', or '微信草稿'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: '一键发布 Markdown 到微信公众号草稿箱' (one-click publish Markdown to WeChat draft), '支持多主题' (multi-theme support), '代码高亮' (code highlighting), '图片自动上传' (auto image upload). Uses third person voice appropriately. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific features, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The when is only implied through the description of capabilities. | 2 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'Markdown', '微信公众号' (WeChat Official Account), '草稿箱' (draft box), '代码高亮' (code highlighting), '图片' (images), and mentions the specific tool 'wenyan-cli'. | 3 / 3 |
Distinctiveness Conflict Risk | Very clear niche targeting WeChat Official Account publishing specifically, with distinct triggers like '微信公众号', 'wenyan-cli', and the specific workflow of Markdown to WeChat draft. Unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, executable guidance with concrete commands and examples, but suffers from severe verbosity and redundancy. The same information (especially frontmatter requirements) is repeated multiple times, and the document includes unnecessary sections (changelog, license, feature lists) that waste tokens. The workflow could benefit from explicit validation checkpoints.
Suggestions
Remove redundant frontmatter explanations - consolidate into one clear example section instead of repeating 4+ times
Delete non-actionable sections (changelog, license, feature checkboxes) that don't help Claude execute the task
Add explicit validation step after publish command (e.g., 'Verify success: check for media_id in response')
Split troubleshooting and theme customization into separate reference files, keeping SKILL.md as a concise quick-start guide
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with significant redundancy. The frontmatter requirements are explained 4+ times with nearly identical examples. Contains unnecessary sections like changelog, license, and feature checkboxes that don't add actionable value. Many concepts are over-explained (e.g., what frontmatter is, multiple ways to specify paths). | 1 / 3 |
Actionability | Provides fully executable commands and code examples throughout. Installation, configuration, and usage commands are copy-paste ready. Multiple concrete examples for different scenarios (themes, paths, troubleshooting commands). | 3 / 3 |
Workflow Clarity | The workflow section exists but is too brief (3 vague steps). While troubleshooting section provides error recovery, there's no validation checkpoint between preparing content and publishing. Missing explicit verification step to confirm successful upload before proceeding to review. | 2 / 3 |
Progressive Disclosure | Content is somewhat organized with headers, but everything is in one monolithic file. Advanced topics (custom themes, troubleshooting) could be split into separate files. The document is ~250 lines when it could be a concise overview with references to detailed guides. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 11 Passed | |
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.